Travelled to:1 × Australia
1 × Austria
Collaborated with:M.Bofill M.Villaret T.G.Dietterich R.L.d.Mántaras C.Sierra
Talks about:reinforc (1) approach (1) probabl (1) weight (1) smooth (1) robust (1) declar (1) action (1) refin (1) learn (1)
Person: Dídac Busquets
DBLP: Busquets:D=iacute=dac
Contributed to:
2010
2002Wrote 2 papers:
- PPDP-2010-BofillBV #approach #declarative #robust #satisfiability
- A declarative approach to robust weighted Max-SAT (MB, DB, MV), pp. 67–76.
- ICML-2002-DietterichBMS #learning #probability #refinement
- Action Refinement in Reinforcement Learning by Probability Smoothing (TGD, DB, RLdM, CS), pp. 107–114.